| dc.contributor | Universidade Estadual Paulista (UNESP) | |
| dc.creator | Marar, João Fernando | |
| dc.creator | Coelho, Helder | |
| dc.date | 2014-05-20T13:25:59Z | |
| dc.date | 2014-05-20T13:25:59Z | |
| dc.date | 2008-01-01 | |
| dc.date.accessioned | 2017-04-05T20:04:13Z | |
| dc.date.available | 2017-04-05T20:04:13Z | |
| dc.identifier | Biosignals 2008: Proceedings of The First International Conference on Bio-inspired Systems and Signal Processing, Vol Ii. Setubal: Insticc-inst Syst Technologies Information Control & Communication, p. 261-268, 2008. | |
| dc.identifier | http://hdl.handle.net/11449/8307 | |
| dc.identifier | WOS:000256983100044 | |
| dc.identifier.uri | http://repositorioslatinoamericanos.uchile.cl/handle/2250/856700 | |
| dc.description | Wavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural network have been developed and reported in the literature. However, most of the aforementioned reports impose many restrictions in the classical backpropagation algorithm, such as low dimensionality, tensor product of wavelets, parameters initialization, and, in general, the output is one dimensional, etc. In order to remove some of these restrictions, a family of polynomial wavelets generated from powers of sigmoid functions is presented. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in pattern recognition tasks. As an example of application for the method proposed, it is studied the exclusive-or (XOR) problem. | |
| dc.language | eng | |
| dc.publisher | Insticc-inst Syst Technologies Information Control & Communication | |
| dc.relation | Biosignals 2008: Proceedings of The First International Conference on Bio-inspired Systems and Signal Processing, Vol Ii | |
| dc.rights | info:eu-repo/semantics/closedAccess | |
| dc.subject | artificial neural network | |
| dc.subject | function approximation | |
| dc.subject | polynomial powers of sigmoid (PPS) | |
| dc.subject | wavelets functions | |
| dc.subject | PPS-Wavelet neural networks | |
| dc.subject | activation functions | |
| dc.subject | feedforward networks | |
| dc.title | Multidimensional polynomial powers of sigmoid (PPS) Wavelet neural networks | |
| dc.type | Otro | |
